{"url":"/task/word-translation","name":"Word Translation","slug":"word-translation","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":125,"papers_with_code":40,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/soundscape-attributes-translation-project","name":"Soundscape Attributes Translation Project (SATP) Dataset","full_name":"","num_papers_in_archive":6},{"url":"/dataset/satp-zsm-stage1","name":"satp-zsm-stage1","full_name":"Replication Data for: Crossing the Linguistic Causeway: A Binational Approach for Translating Soundscape Attributes to zsm","num_papers_in_archive":2},{"url":"/dataset/satp-zsm-stage2","name":"satp-zsm-stage2","full_name":"Replication data for Crossing the Linguistic Causeway: Ethnonational Differences on Soundscape Attributes in Bahasa Melayu","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":40,"tagged_in_all":125,"items":[{"url":"/paper/word-translation-without-parallel-data","title":"Word Translation Without Parallel Data","date":"2017-10-11","arxiv_id":"1710.04087","repositories_listed":20,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":8}},{"url":"/paper/loss-in-translation-learning-bilingual-word","title":"Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion","date":"2018-04-20","arxiv_id":"1804.07745","repositories_listed":4,"syntology":null},{"url":"/paper/non-adversarial-unsupervised-word-translation","title":"Non-Adversarial Unsupervised Word Translation","date":"2018-01-18","arxiv_id":"1801.06126","repositories_listed":4,"syntology":null},{"url":"/paper/unsupervised-multilingual-word-embeddings","title":"Unsupervised Multilingual Word Embeddings","date":"2018-08-27","arxiv_id":"1808.08933","repositories_listed":3,"syntology":null},{"url":"/paper/lexc-gen-generating-data-for-extremely-low","title":"LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons","date":"2024-02-21","arxiv_id":"2402.14086","repositories_listed":2,"syntology":null},{"url":"/paper/robust-cross-lingual-embeddings-from-parallel-1","title":"Robust Cross-lingual Embeddings from Parallel Sentences","date":"2019-12-28","arxiv_id":"1912.12481","repositories_listed":2,"syntology":null},{"url":"/paper/learning-multilingual-word-embeddings-in","title":"Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approach","date":"2018-08-27","arxiv_id":"1808.08773","repositories_listed":2,"syntology":null},{"url":"/paper/cross-lingual-adaptation-using-structural","title":"Cross-Lingual Adaptation using Structural Correspondence Learning","date":"2010-08-04","arxiv_id":"1008.0716","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reasoning-translation-via-reinforcement","title":"Deep Reasoning Translation via Reinforcement Learning","date":"2025-04-14","arxiv_id":"2504.10187","repositories_listed":1,"syntology":null},{"url":"/paper/separating-tongue-from-thought-activation","title":"Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers","date":"2024-11-13","arxiv_id":"2411.08745","repositories_listed":1,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":10}},{"url":"/paper/optimizing-rare-word-accuracy-in-direct","title":"Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach","date":"2024-09-13","arxiv_id":"2409.09009","repositories_listed":1,"syntology":null},{"url":"/paper/improving-rare-word-translation-with","title":"Improving Rare Word Translation With Dictionaries and Attention Masking","date":"2024-08-17","arxiv_id":"2408.09075","repositories_listed":1,"syntology":null},{"url":"/paper/self-augmented-in-context-learning-for","title":"Self-Augmented In-Context Learning for Unsupervised Word Translation","date":"2024-02-15","arxiv_id":"2402.10024","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/fingerspelling-posenet-enhancing","title":"Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models","date":"2023-11-20","arxiv_id":"2311.12128","repositories_listed":1,"syntology":null},{"url":"/paper/promap-effective-bilingual-lexicon-induction","title":"ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting","date":"2023-10-28","arxiv_id":"2310.18778","repositories_listed":1,"syntology":null},{"url":"/paper/on-bilingual-lexicon-induction-with-large","title":"On Bilingual Lexicon Induction with Large Language Models","date":"2023-10-21","arxiv_id":"2310.13995","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/transdocs-optical-character-recognition-with","title":"TransDocs: Optical Character Recognition with word to word translation","date":"2023-04-15","arxiv_id":"2304.07637","repositories_listed":1,"syntology":null},{"url":"/paper/peach-pre-training-sequence-to-sequence","title":"PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation","date":"2023-04-03","arxiv_id":"2304.01282","repositories_listed":1,"syntology":null},{"url":"/paper/towards-making-the-most-of-chatgpt-for","title":"Towards Making the Most of ChatGPT for Machine Translation","date":"2023-03-24","arxiv_id":"2303.13780","repositories_listed":1,"syntology":null},{"url":"/paper/improving-bilingual-lexicon-induction-with-1","title":"Improving Bilingual Lexicon Induction with Cross-Encoder Reranking","date":"2022-10-30","arxiv_id":"2210.16953","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/utilizing-language-image-pretraining-for","title":"Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment","date":"2022-05-23","arxiv_id":"2205.11616","repositories_listed":1,"syntology":null},{"url":"/paper/redistributing-low-frequency-words-making-the-1","title":"Redistributing Low-Frequency Words: Making the Most of Monolingual Data in Non-Autoregressive Translation","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bridging-cross-lingual-gaps-during-leveraging","title":"Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding","date":"2022-04-16","arxiv_id":"2204.07834","repositories_listed":1,"syntology":null},{"url":"/paper/improving-word-translation-via-two-stage-1","title":"Improving Word Translation via Two-Stage Contrastive Learning","date":"2022-03-15","arxiv_id":"2203.08307","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/improving-word-translation-via-two-stage","title":"Improving Word Translation via Two-Stage Contrastive Learning","date":"2021-11-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-computational-linguistics-in","title":"Towards Computational Linguistics in Minangkabau Language: Studies on Sentiment Analysis and Machine Translation","date":"2020-09-19","arxiv_id":"2009.09309","repositories_listed":1,"syntology":null},{"url":"/paper/bilingual-dictionary-based-neural-machine-1","title":"Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences","date":"2020-07-06","arxiv_id":"2007.02671","repositories_listed":1,"syntology":null},{"url":"/paper/learning-and-evaluating-emotion-lexicons-for","title":"Learning and Evaluating Emotion Lexicons for 91 Languages","date":"2020-05-12","arxiv_id":"2005.05672","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/multiseg-parallel-data-and-subword","title":"MultiSeg: Parallel Data and Subword Information for Learning Bilingual Embeddings in Low Resource Scenarios","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/visual-grounding-in-video-for-unsupervised","title":"Visual Grounding in Video for Unsupervised Word Translation","date":"2020-03-11","arxiv_id":"2003.05078","repositories_listed":1,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}